scimilarity.nn_models#

This file contains the neural network architectures. These are all you need for inference.

class scimilarity.nn_models.Decoder(n_genes, latent_dim=128, hidden_dim=[1024, 1024], dropout=0.5)[source]#

Bases: Module

A class that encapsulates the decoder.

Parameters:

  • n_genes (int) – The number of genes in the gene space, representing the input dimensions.

  • latent_dim (int, default: 128) – The latent space dimensions

  • hidden_dim (List[int], default: [1024, 1024]) – A list of hidden layer dimensions, describing the number of layers and their dimensions. Hidden layers are constructed in the order of the list for the encoder and in reverse for the decoder.

  • dropout (float, default: 0.5) – The dropout rate for hidden layers

forward(x)[source]#

Forward.

Parameters:

x (torch.Tensor) – Input tensor corresponding to input layer.

Returns:

Output tensor corresponding to output layer.

Return type:

torch.Tensor

load_state(filename, use_gpu=False)[source]#

Load model state.

Parameters:

  • filename (str) – Filename containing the model state.

  • use_gpu (bool, default: False) – Boolean indicating whether or not to use GPUs.

save_state(filename)[source]#

Save model state.

Parameters:

filename (str) – Filename to save the model state.

class scimilarity.nn_models.Encoder(n_genes, latent_dim=128, hidden_dim=[1024, 1024], dropout=0.5, input_dropout=0.4)[source]#

Bases: Module

A class that encapsulates the encoder.

Parameters:

  • n_genes (int) – The number of genes in the gene space, representing the input dimensions.

  • latent_dim (int, default: 128) – The latent space dimensions

  • hidden_dim (List[int], default: [1024, 1024]) – A list of hidden layer dimensions, describing the number of layers and their dimensions. Hidden layers are constructed in the order of the list for the encoder and in reverse for the decoder.

  • dropout (float, default: 0.5) – The dropout rate for hidden layers

  • input_dropout (float, default: 0.4) – The dropout rate for the input layer

forward(x)[source]#

Forward.

Parameters:

x (torch.Tensor) – Input tensor corresponding to input layer.

Returns:

Output tensor corresponding to output layer.

Return type:

torch.Tensor

load_state(filename, use_gpu=False)[source]#

Load model state.

Parameters:

  • filename (str) – Filename containing the model state.

  • use_gpu (bool, default: False) – Boolean indicating whether or not to use GPUs.

save_state(filename)[source]#

Save model state.

Parameters:

filename (str) – Filename to save the model state.